© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 24943
    Prev
    Next
    INDEX
    Explanations

    stock photos and royalties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ocities
    -0.12
     pdf
    -0.10
    icum
    -0.10
     PDF
    -0.10
    Vi
    -0.09
     Wen
    -0.09
    herit
    -0.09
     Posting
    -0.09
     Comic
    -0.09
    quine
    -0.09
    POSITIVE LOGITS
     royalty
    0.16
     Roy
    0.16
     Shutterstock
    0.13
    Roy
    0.12
     royalties
    0.12
    Stock
    0.12
    utterstock
    0.11
     stock
    0.11
     Stock
    0.11
    roy
    0.11
    Activations Density 0.251%

    No Known Activations